Zero Shot Coordination

Zero-shot coordination (ZSC) in multi-agent systems focuses on developing agents capable of seamlessly collaborating with unseen partners without prior interaction. Current research emphasizes improving the generalization ability of reinforcement learning agents, exploring diverse model architectures like program-based policies and equivariant networks, and employing techniques such as population-based training, co-evolution, and intrinsic reward shaping to enhance adaptability and robustness. This field is crucial for advancing human-AI collaboration and building more flexible, scalable, and reliable multi-agent systems for applications ranging from robotics to autonomous driving.

Papers

November 7, 2024

Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games
Usman Anwar, Ashish Pandian, Jia Wan, David Krueger, Jakob Foerster
Reinforcement Learning Zero Shot Coordination

November 2, 2024

Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactions
Weifan Long, Wen Wen, Peng Zhai, Lihua Zhang
Multi Agent Reinforcement Learning Interaction Strategy Role Play Zero Shot Coordination Adaptive Strategy Role Based Mixed Motive

September 13, 2024

HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit
Yang Li, Dengyu Zhang, Junfan Chen, Ying Wen, Qingrui Zhang, Shaoshuai Mou, Wei Pan
Zero Shot Coordination Open Domain Generative

August 8, 2024

KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination
Yin Gu, Qi Liu, Zhi Li, Kai Zhang
Deep Reinforcement Learning Zero Shot Coordination Cooperative AI Programmatic Reinforcement Learning

June 25, 2024

The Overcooked Generalisation Challenge
Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling
Cooperative Multi Agent System Zero Shot Coordination Human AI Cooperation

April 5, 2024

Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration
Xudong Guo, Daming Shi, Junjie Yu, Wenhui Fan
Multi Agent Reinforcement Learning Proximal Policy Optimization Multi Agent Challenge Zero Shot Coordination PPO Algorithm Heterogeneous Multi Agent Reinforcement Learning Real World Multi Agent

February 26, 2024

Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition
Dylan Cope, Peter McBurney
Imitation Learning Emergent Communication Language Acquisition Zero Shot Coordination Translation Based

October 8, 2023

ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
Xihuai Wang, Shao Zhang, Wenhao Zhang, Wentao Dong, Jingxiao Chen, Ying Wen, Weinan Zhang
New Benchmark Generalization Performance Cooperative Multi Agent Reinforcement Learning G Eval Zero Shot Coordination

October 5, 2023

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
Saaket Agashe, Yue Fan, Anthony Reyna, Xin Eric Wang
LLM Benchmark Multi Agent Coordination Zero Shot Coordination Emergent Reasoning

August 22, 2023

ProAgent: Building Proactive Cooperative Agents with Large Language Models
Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang
Multi Agent System AI Agent Cooperative Agent Zero Shot Coordination

August 20, 2023

Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi
Hadi Nekoei, Xutong Zhao, Janarthanan Rajendran, Miao Liu, Sarath Chandar
Multi Agent Cooperative Multi Agent Reinforcement Learning Game Content Ad Hoc Zero Shot Coordination Independent Q Learning Game Hanabi

June 5, 2023

Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination
Yang Li, Shao Zhang, Jichen Sun, Wenhao Zhang, Yali Du, Ying Wen, Xinbing Wang, Wei Pan
Zero Shot Open Ended Cooperative Game Zero Shot Coordination Self Compatibility Human AI Coordination

May 31, 2023

Adaptive Coordination in Social Embodied Rearrangement
Andrew Szot, Unnat Jain, Dhruv Batra, Zsolt Kira, Ruta Desai, Akshara Rai
Coordinated Behavior Zero Shot Coordination Adaptive Agent Behavioral Diversity Eye Hand Coordination

February 10, 2023

Improving Zero-Shot Coordination Performance Based on Policy Similarity
Lebin Yu, Yunbo Qiu, Quanming Yao, Xudong Zhang, Jian Wang
Multi Agent Reinforcement Learning Self Play Zero Shot Coordination Policy Similarity Complex Coordination

February 9, 2023

Cooperative Open-ended Learning Framework for Zero-shot Coordination
Yang Li, Shao Zhang, Jichen Sun, Yali Du, Ying Wen, Xinbing Wang, Wei Pan
Open Ended Cooperative Game Zero Shot Coordination Cooperative AI

January 16, 2023

PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination
Xingzhou Lou, Jiaxian Guo, Junge Zhang, Jun Wang, Kaiqi Huang, Yali Du
Content Addressable Memory Zero Shot Coordination Human AI Coordination Ensemble Deep Reinforcement Learning

October 21, 2022

Equivariant Networks for Zero-Shot Coordination
Darius Muglich, Christian Schroeder de Witt, Elise van der Pol, Shimon Whiteson, Jakob Foerster
Equivariant Network Partial Observability Self Play Zero Shot Coordination

October 9, 2022

ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward
Zixian Ma, Rose Wang, Li Fei-Fei, Michael Bernstein, Ranjay Krishna
Multi Agent Reinforcement Learning Intrinsic Reward Expectation Alignment Multi Agent Particle Zero Shot Coordination

August 9, 2022

Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution
Ke Xue, Yutong Wang, Cong Guan, Lei Yuan, Haobo Fu, Qiang Fu, Chao Qian, Yang Yu
Zero Shot Coordination Adaptive Coevolution Agent Generation

July 14, 2022

K-level Reasoning for Zero-Shot Coordination in Hanabi
Brandon Cui, Hengyuan Hu, Luis Pineda, Jakob N. Foerster
Ad Hoc Zero Shot Coordination Artificial Intelligence Performance Game Hanabi K Level Reasoning

Zero Shot Coordination

Papers

Noisy Zero-Shot Coordination: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games

Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactions

HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit

KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination

The Overcooked Generalisation Challenge

Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration

Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition

ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi

Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination

Adaptive Coordination in Social Embodied Rearrangement

Improving Zero-Shot Coordination Performance Based on Policy Similarity

Cooperative Open-ended Learning Framework for Zero-shot Coordination

PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination

Equivariant Networks for Zero-Shot Coordination

ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward

Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution

K-level Reasoning for Zero-Shot Coordination in Hanabi